中文
相关论文

相关论文: Adaptive Batch Size and Learning Rate Scheduler fo…

200 篇论文

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

机器学习 · 计算机科学 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

机器学习 · 计算机科学 2020-03-04 Achraf Bahamou , Donald Goldfarb

We consider the setting where a master wants to run a distributed stochastic gradient descent (SGD) algorithm on $n$ workers, each having a subset of the data. Distributed SGD may suffer from the effect of stragglers, i.e., slow or…

机器学习 · 计算机科学 2022-08-08 Serge Kas Hanna , Rawad Bitar , Parimal Parag , Venkat Dasari , Salim El Rouayheb

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate…

机器学习 · 统计学 2020-08-28 Antti Koskela , Antti Honkela

Stochastic Gradient Descent (SGD) is a popular optimization method which has been applied to many important machine learning tasks such as Support Vector Machines and Deep Neural Networks. In order to parallelize SGD, minibatch training is…

机器学习 · 统计学 2014-05-14 Peilin Zhao , Tong Zhang

We analyze the convergence behavior of stochastic gradient descent with momentum (SGDM) under dynamic learning-rate and batch-size schedules by introducing a novel and simpler Lyapunov function. We extend the existing theoretical framework…

机器学习 · 计算机科学 2025-10-13 Yuichi Kondo , Hideaki Iiduka

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

机器学习 · 统计学 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent…

机器学习 · 统计学 2018-10-30 Ashok Cutkosky , Robert Busa-Fekete

We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive regularization is imposed by stochastic process in determining…

机器学习 · 计算机科学 2020-04-15 Kensuke Nakamura , Stefano Soatto , Byung-Woo Hong

We study the asynchronous stochastic gradient descent algorithm for distributed training over $n$ workers which have varying computation and communication frequency over time. In this algorithm, workers compute stochastic gradients in…

机器学习 · 计算机科学 2022-06-17 Anastasia Koloskova , Sebastian U. Stich , Martin Jaggi

It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as,…

最优化与控制 · 数学 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often…

最优化与控制 · 数学 2019-05-06 Sebastian U. Stich

Stochastic gradient descent (SGD) is an estimation tool for large data employed in machine learning and statistics. Due to the Markovian nature of the SGD process, inference is a challenging problem. An underlying asymptotic normality of…

统计计算 · 统计学 2025-03-27 Rahul Singh , Abhinek Shukla , Dootika Vats

The stochastic gradient descent (SGD) optimization algorithm plays a central role in a series of machine learning applications. The scientific literature provides a vast amount of upper error bounds for the SGD method. Much less attention…

数值分析 · 数学 2020-10-05 Arnulf Jentzen , Philippe von Wurstemberger

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

机器学习 · 计算机科学 2017-11-23 Haiping Huang , Taro Toyoizumi

This paper proposes SplitSGD, a new dynamic learning rate schedule for stochastic optimization. This method decreases the learning rate for better adaptation to the local geometry of the objective function whenever a stationary phase is…

机器学习 · 统计学 2024-02-20 Matteo Sordello , Niccolò Dalmasso , Hangfeng He , Weijie Su

Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization…

机器学习 · 计算机科学 2024-09-17 Haihan Zhang , Yuanshi Liu , Qianwen Chen , Cong Fang

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence…

机器学习 · 计算机科学 2025-07-03 Di Zhang , Yihang Zhang

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

机器学习 · 计算机科学 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm…

机器学习 · 计算机科学 2024-05-29 Tim Tsz-Kit Lau , Han Liu , Mladen Kolar